Host: The Japanese Society for Artificial Intelligence
Name : 34th Annual Conference, 2020
Number : 34
Location : Online
Date : June 09, 2020 - June 12, 2020
Understanding correlations between real estate floor plans and their inherent qualities in a quantitative data format would be important in order to obtain deep neural networks that could extract features related to the attractiveness of apartments. This paper presents the creation and analysis of the large-scale dataset of real estate floor plan images with attractiveness evaluation data. We collected the evaluation through crowdsourcing by using nine statements that explore qualitative and functional values of apartments such as a level of comfort, perceived size, modernity, and so on. We found that the users’ attributes such as their ages, genders, marital statuses, and family structures can influence their preferences of apartment floor plans. Results revealed several characteristics that matched with our general preferences for apartments.